SEEDANCE25APIINDEPENDENT
EN / 中文 Get API key

AGENT MODE / SEEDANCE 2.5 API

Give your coding agent the right context before it writes code.

This page is for Cursor, Claude Code, Codex, ChatGPT, and other agents integrating Seedance 2.5 API for a human. Copy the instruction block, let the agent read the machine files, then create a provider key only when the code is ready.

Open llms-full.txt Open OpenAPI
01 / CONTEXTCOPY THIS FIRST
AGENT_PROMPT.TXTHUMAN -> AGENT
You are helping me integrate the Seedance 2.5 API.

Primary context: https://seedance25api.io/llms-full.txt
Request schema: https://seedance25api.io/openapi.json

Rules:
- Do not invent or hardcode an API key.
- Ask me to create EVOLINK_API_KEY before any live call: https://evolink.ai/dashboard/keys?utm_source=seedance25api.io&utm_medium=referral&utm_campaign=agent&utm_content=agent-prompt
- Keep the model configurable. Seedance 2.5 API access is expected; verify provider support before production.
- Public rates are not published yet — surface cost as an estimate and flag it.
- Validate duration, resolution, and reference counts before sending.
- Use polling or callback_url for async video jobs.
- Build behind a configurable model parameter so the same code can switch models.

Why this works

The agent gets stable context URLs, a schema, a key boundary, and the exact provider handoff. It can prepare code without pretending it already has credentials.

Create API key
02 / MACHINE FILESWHAT AGENTS SHOULD READ
/llms.txtShort index for LLMs and search agents. /llms-full.txtFull context: facts, status, schema, pricing notes, handoff. /agent.mdMarkdown checklist for coding agents. /openapi.jsonRequest contract for API clients and codegen.
03 / FACTSSTATUS-AWARE INTEGRATION
Expected

Provider-mediated access

Seedance 2.5 API availability should be verified with the provider before production use. Build behind a configurable model parameter.

Expected

Reference-to-video model ID

seedance-2.5-reference-to-video

Confirmed in EvoLink API docs; model is pre-release ("not yet available"). References are optional, so a prompt-only call behaves as text-to-video.

Pending

Text-to-video / image-to-video IDs

Pending provider docs

Not yet confirmed. Keep the model parameter configurable so the same code can switch when the IDs are published.

Expected

Launch limits

4-30 seconds · 480p and 720p

Validate duration, quality, and reference counts (up to 30 image / 10 video / 10 audio) before sending.

04 / AGENT CHECKLISTBEFORE LIVE CALLS
  1. Do not invent or hardcode an API key.
  2. Ask the human to create EVOLINK_API_KEY before live calls.
  3. Build behind a configurable model parameter.
  4. Surface cost as an estimate — public rates are not published yet.
  5. Validate duration, quality, and reference counts before sending.
  6. Use polling or callback_url for async completion.
  7. If the model is unavailable for the account, keep the request shape and switch models via the configurable parameter once access is enabled.